view mercurial/repocache.py @ 42619:20d0e59be79b

tests: show the files fields of changelogs for many merges

I don't think there's coverage for many of the subtle cases, and I
found it hard to understand what the code is doing by reading it.  The
test takes 40s to run on a laptop, or 9s with --chg.

I have yet to find a description of what the files field is supposed
to be for merges. I thought it could be one of:
1. the files added/modified/removed relative to p1 (wouldn't seem
  useful, but `hg diff -c -r mergerev` has this behavior)
2. the files with filelog nodes not in either parent (i.e., what is
needed to create a bundle out of a commit)
3. the files added/removed/modified files by merge itself [1]

It's clearly not 1, because file contents merges are symmetric. It's
clearly not 2 because removed files and exec bit changes are
listed. It's also not 3 but I think it's intended to be 3 and the
differences are bugs.

Assuming 3, the test shows that, for merges, the list of files both
overapproximates and underapproximates. All the cases involve file
changes not in the filelog but in the manifest (existence of file
at revision, exec bit and file vs symlink).

I didn't look at all underapproximations, but they looked minor. The
two overapproximations are problematic though because they both cause
potentially long lists of files when merging cleanly.


[1] even what it means for the merge commit itself to change a file is
not completely trivial. A file in the merge being the same as in one
of the parent is too lax as it would consider that merges change
nothing when they revert all the changes done on one side. The
criteria used in the test and in the next commit for "merge didn't
touch a file" is:
- the parents and the merge all have the same file
- or, one parent didn't touch the file and the other parent contains
  the same file as the merge

Differential Revision: https://phab.mercurial-scm.org/D6612

# repocache.py - in-memory repository cache for long-running services
#
# Copyright 2018 Yuya Nishihara <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import collections
import gc
import threading

from . import (
    error,
    hg,
    obsolete,
    scmutil,
    util,
)

class repoloader(object):
    """Load repositories in background thread

    This is designed for a forking server. A cached repo cannot be obtained
    until the server fork()s a worker and the loader thread stops.
    """

    def __init__(self, ui, maxlen):
        self._ui = ui.copy()
        self._cache = util.lrucachedict(max=maxlen)
        # use deque and Event instead of Queue since deque can discard
        # old items to keep at most maxlen items.
        self._inqueue = collections.deque(maxlen=maxlen)
        self._accepting = False
        self._newentry = threading.Event()
        self._thread = None

    def start(self):
        assert not self._thread
        if self._inqueue.maxlen == 0:
            # no need to spawn loader thread as the cache is disabled
            return
        self._accepting = True
        self._thread = threading.Thread(target=self._mainloop)
        self._thread.start()

    def stop(self):
        if not self._thread:
            return
        self._accepting = False
        self._newentry.set()
        self._thread.join()
        self._thread = None
        self._cache.clear()
        self._inqueue.clear()

    def load(self, path):
        """Request to load the specified repository in background"""
        self._inqueue.append(path)
        self._newentry.set()

    def get(self, path):
        """Return a cached repo if available

        This function must be called after fork(), where the loader thread
        is stopped. Otherwise, the returned repo might be updated by the
        loader thread.
        """
        if self._thread and self._thread.is_alive():
            raise error.ProgrammingError(b'cannot obtain cached repo while '
                                         b'loader is active')
        return self._cache.peek(path, None)

    def _mainloop(self):
        while self._accepting:
            # Avoid heavy GC after fork(), which would cancel the benefit of
            # COW. We assume that GIL is acquired while GC is underway in the
            # loader thread. If that isn't true, we might have to move
            # gc.collect() to the main thread so that fork() would never stop
            # the thread where GC is in progress.
            gc.collect()

            self._newentry.wait()
            while self._accepting:
                self._newentry.clear()
                try:
                    path = self._inqueue.popleft()
                except IndexError:
                    break
                scmutil.callcatch(self._ui, lambda: self._load(path))

    def _load(self, path):
        start = util.timer()
        # TODO: repo should be recreated if storage configuration changed
        try:
            # pop before loading so inconsistent state wouldn't be exposed
            repo = self._cache.pop(path)
        except KeyError:
            repo = hg.repository(self._ui, path).unfiltered()
        _warmupcache(repo)
        repo.ui.log(b'repocache', b'loaded repo into cache: %s (in %.3fs)\n',
                    path, util.timer() - start)
        self._cache.insert(path, repo)

# TODO: think about proper API of preloading cache
def _warmupcache(repo):
    repo.invalidateall()
    repo.changelog
    repo.obsstore._all
    repo.obsstore.successors
    repo.obsstore.predecessors
    repo.obsstore.children
    for name in obsolete.cachefuncs:
        obsolete.getrevs(repo, name)
    repo._phasecache.loadphaserevs(repo)

# TODO: think about proper API of attaching preloaded attributes
def copycache(srcrepo, destrepo):
    """Copy cached attributes from srcrepo to destrepo"""
    destfilecache = destrepo._filecache
    srcfilecache = srcrepo._filecache
    if 'changelog' in srcfilecache:
        destfilecache['changelog'] = ce = srcfilecache['changelog']
        ce.obj.opener = ce.obj._realopener = destrepo.svfs
    if 'obsstore' in srcfilecache:
        destfilecache['obsstore'] = ce = srcfilecache['obsstore']
        ce.obj.svfs = destrepo.svfs
    if '_phasecache' in srcfilecache:
        destfilecache['_phasecache'] = ce = srcfilecache['_phasecache']
        ce.obj.opener = destrepo.svfs